Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_20b9f688-742f-4a8f-8955-04d57f566697.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: accra\n[strong] Accra -> CLICK\n[option] One way -> CLICK\n[gridcell] 14 April 2023 -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.28, 0.94, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/69661946-6c3e-4e26-95ed-1f7641a31f22_deaf5409-9171-444b-af73-c5f6b73aec49.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse listings for a used Toyota Corolla near 10019 and sort by cheapest.\nPrevious actions:\n[LabelText] Buy Used -> CLICK\n[combobox] Select Make -> SELECT: Toyota\n[combobox] Select Model -> SELECT: Corolla" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.521, 0.19, 0.599, 0.211] in the image\nAnd my action is Action: TYPE\nValue: 10019" } ]

{ "bytes": "", "path": "./images/57f72023-3633-4c97-93f6-af12fe2edf4f_b84e4315-a4fa-4c98-85d7-362aa485addc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\n[searchbox] Search -> TYPE: SOUTH AFRICAN HISTORY PODCAST\n[button] Search -> CLICK\n[link] Tracks -> CLICK\n[link] Any length -> CLICK\n[link] 10-30 min -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.347, 0.108, 0.357] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_af8d6e2e-cb67-4ba2-b95d-734aeb121700.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[link] Pants -> CLICK\n[gridcell] Category -> CLICK\n[input] -> CLICK\n[option] Sweatpants -> CLICK\n[heading] Sweatpants -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.778, 0.184, 0.806, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d070774f-9ca2-43c0-a7d0-221697791cf0_363d203f-3721-4830-bd17-b3ba4819cdb4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a place with a good swimming pool that charges between $200 and $300 per night.\nPrevious actions:\n[img] -> CLICK\n[span] Filters -> CLICK\n[textbox] min price $ -> TYPE: 200\n[textbox] max price $ -> TYPE: 400" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.478, 0.786, 0.502] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1df0723c-f732-4ecb-b202-8e1854b7c079_e1d49b1d-8ccb-40dc-b6ed-08c19adbb66b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of rental vehicles for Brooklyn, OH, US for 18 year old renter.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: Brooklyn\n[option] Brooklyn, OH, US Select -> CLICK\n[combobox] Renter Age -> SELECT: 18" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.341, 0.837, 0.365] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_9a06fdfb-25fa-4319-903f-ca492483c9fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[input] -> CLICK\n[option] Relaxed Wireless -> CLICK\n[heading] Size -> CLICK\n[label] XXS -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.212, 0.256, 0.392] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_5e1e5cf7-2414-4425-a730-3a1d08d2897a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[span] -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] Depart , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.509, 0.28, 0.693, 0.31] in the image\nAnd my action is Action: TYPE\nValue: 04/22/2023" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_ffd68484-58e9-46e4-9d94-e0aa3514e9fd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[button] pickup time input field -> CLICK\n[button] Confirm -> CLICK\n[combobox] Passengers -> SELECT: 2\n[button] Search -> CLICK\n[button] Choose a standard-size taxi costing US$126.84 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.855, 0.53, 0.988, 0.585] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_9edd8d21-46ba-4b5e-a9c2-d5677b6f439f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] To -> TYPE: NEW YORK\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] Select a trip start date -> CLICK\n[gridcell] Wednesday, April 5, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.266, 0.795, 0.283] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_6017cb86-e365-4f2e-ae94-89c66c382a9b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[link] Footwear -> CLICK\n[menuitem] Hiking Boots -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.502, 0.068, 0.51] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_e2eb86ff-e660-46d6-a5d8-7109a895d213.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[tab] Flights -> CLICK\n[tab] One-way -> CLICK\n[button] Leaving from -> CLICK\n[textbox] Leaving from -> TYPE: jfk" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.136, 0.362, 0.16] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0db002f6-db7d-4382-9c0d-8f5cef2afa17_134500d5-c3c2-4f6e-b266-64e10e38b77a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find detailed uses of Anuall Pass for 2023 on the USGS Online\nPrevious actions:\n[link] Passes -> CLICK\n[link] Annual Pass -> CLICK\n[button] Overview of the Annual Pass -> CLICK\n[button] Annual Pass Internet Order Questions -> CLICK\n[button] Annual Pass Use -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.803, 0.95, 0.837] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86ea50f5-1310-456e-97bf-799d8eb1896b_3a8e2481-e070-4ea5-8ff9-d87a03299985.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the NFL Passing yards players stats.\nPrevious actions:\n[link] National Football League NFL -> CLICK\n[button] Open More Dropdown -> CLICK\n[heading] STATS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.51, 0.11, 0.693, 0.18] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/196cde81-b001-47ec-b7c3-a77869e36deb_9712bbdc-3c5d-417f-b2d8-d9532b8fd75f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check bookstores available in Chelsea area\nPrevious actions:\n[link] shopping. -> CLICK\n[li] Neighborhood -> CLICK\n[link] Chelsea -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.111, 0.206, 0.119] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_14d7f372-72b4-45e3-9082-e6915b5bce86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[searchbox] Search -> TYPE: gobites uno spork\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.247, 0.225, 0.473, 0.382] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_a9db226a-fd14-429d-9f96-905cb66d254e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[span] 20 -> CLICK\n[button] Done -> CLICK\n[button] 1 Room, 1 Guest -> CLICK\n[button] Add Rooms -> CLICK\n[button] Add Adults -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.13, 0.341, 0.143] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d6c1c4f5-74a7-4451-8dd2-aabada5d7ba1_4993fb7b-d906-4cad-8fa3-13bfe605511b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find rental charges for bikes in 37863.\nPrevious actions:\n[link] Find a Store -> CLICK\n[textbox] Enter ZIP or City, State -> TYPE: 37863\n[path] -> CLICK\n[generic] Bike shop Pigeon Forge -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.431, 0.886, 0.561, 0.906] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_74e08d5f-5c4d-4ca2-9071-4ca8955b2592.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\n[span] Cannes -> CLICK\n[link] 2022 -> CLICK\n[link] Eo -> CLICK\n[button] ​Jerzy Skolimowski -> CLICK\n[button] Add to list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.278, 0.509, 0.722, 0.54] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_84ac998d-2de1-42a7-802a-4df326c3ff1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[textbox] From -> TYPE: WASHINGTON\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] To -> TYPE: NEW YORK\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] Select a trip start date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.705, 0.221, 0.73, 0.242] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_b0b71afe-6f0d-43ef-84e1-9739bd184012.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[div] -> CLICK\n[generic] 15 -> CLICK\n[generic] 16 -> CLICK\n[button] 11:30 -> CLICK\n[button] 11:00 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.115, 0.953, 0.141] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ce34bc61-e3d2-40c8-b02b-b149efc4b115_25ed6cca-1f43-4bd0-a185-8d4db5e858e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.28, 0.84, 0.315] in the image\nAnd my action is Action: TYPE\nValue: Brooklyn" } ]

{ "bytes": "", "path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_c88d4a1e-9abf-487f-886a-34ca0b837800.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Close -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[button] Add to playlist -> CLICK\n[button] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.407, 0.229, 0.456, 0.238] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bb8d48f-dac7-472d-b2b2-651ab184baf2_15e83256-e4cc-4937-b835-1cf9ab6b1cee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a hybrid job at Resy in software development, if the job is open apply immediately.\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.658, 0.452, 0.683] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8a6f2641-9896-4657-b447-56927420e8c4_8c9d79e2-b2a1-4197-9879-8ef7936e9e85.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[checkbox] Educational Educational -> CLICK\n[button] Done -> CLICK\n[button] Best Matches -> CLICK\n[link] Price Low To High -> CLICK\n[link] Comic Coloring Book - Nintendo Switch -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.962, 0.424, 0.991, 0.435] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_2a40aabf-98f7-48bd-863b-0f5a3dd0ebb3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[span] Black -> CLICK\n[button] Next -> CLICK\n[button] None -> CLICK\n[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.334, 0.284, 0.368] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/440273fa-f1b0-41e8-be75-90732ad5170d_ecb3d820-f6e3-4ffb-84c9-e31d01c412bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Mens size guide for bottoms\nPrevious actions:\n[link] Size Guide -> CLICK\n[link] Men -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.465, 0.351, 0.557, 0.367] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ad381d87-53a0-4aa1-a1e5-d6d172a905cd_b211b155-4276-43bf-9669-5973995ff7f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the women cropped tops with lowest price first.\nPrevious actions:\n[link] WOMEN -> CLICK\n[link] Cropped Tops -> CLICK\n[generic] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.761, 0.234, 0.943, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_a81330b9-cafd-455a-851e-4c12df331c37.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York\n[li] New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.328, 0.195, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_a939b3d8-1cd7-4b45-9cd1-3ef535f86ff7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[menuitem] Women -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.431, 0.133, 0.449] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5098c679-dacc-4abd-9331-18b898f936dd_37627ad6-4621-4127-bbeb-101ffa0b748f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the St louis park policies regarding security?\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags St. Louis -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.749, 0.166, 0.86, 0.181] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a9b1b45-cb23-4073-897f-67410087df9d_e2409464-38c3-4846-b44d-16d5e4f8752c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule COVID-19 test appointment at 90028.\nPrevious actions:\n[span] COVID-19 booster, testing, treatment & records -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.317, 0.765, 0.485, 0.78] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e1a344d-a27b-4613-8863-7afad0829b23_726244d6-5065-4024-9dad-6bf45baea932.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest washable blue rug under 2'x3' size.\nPrevious actions:\n[link] For the Home -> HOVER\n[link] Rugs -> CLICK\n[link] Washable Rugs Washable Rugs -> CLICK\n[span] Color -> CLICK\n[link] Blue (237) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.355, 0.034, 0.367] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7cee0c0-b67d-46b8-bbd1-9f042fe810f5_9d7d0da5-57b8-4690-83ca-7ac5bc0523d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking for 123456 last name Smith.\nPrevious actions:\n[tab] My Trips -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.357, 0.353, 0.397] in the image\nAnd my action is Action: TYPE\nValue: 123456" } ]

{ "bytes": "", "path": "./images/1d0dcb84-da65-4830-ba60-cc2b09a52a13_92f2909f-c267-419a-b4e0-2a5ec5b1fae2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\n[checkbox] Gray 12 products -> CLICK\n[button] Show filter modal Material -> CLICK\n[span] -> CLICK\n[span] Plastic -> CLICK\n[button] Show sorting options modal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.272, 0.619, 0.307, 0.657] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f0d7056-07f8-48b3-8093-e48abb301018_dc4a1187-c24d-4f06-bcad-066836cd1a30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What is the cheapest luxury car to pickup on the second closest nearby location to New York, United States, 100\nPrevious actions:\n[link] Luxury Car Rental -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: New York, United States, 100" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.043, 0.426, 0.064] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_7c35e712-8cec-40c1-baa4-93011d5f7d76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[path] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.433, 0.139, 0.469] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/716ed90e-a138-452e-b5b5-167911871fda_4a544b84-9172-41ad-aa8a-e19736c63137.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find Playstation gift card of $10.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: playstation gift card $10\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.319, 0.179, 0.472] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_6b765434-a76e-4653-b427-7662d96ba478.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[svg] -> CLICK\n[div] -> CLICK\n[checkbox] Avis -> CLICK\n[button] More filters -> CLICK\n[checkbox] 4+ doors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.551, 0.373, 0.56] in the image\nAnd my action is Action: TYPE\nValue: 1000" } ]

{ "bytes": "", "path": "./images/db72bae1-ff16-495c-89c7-1cff7c0ae503_081badf7-327c-4983-a9e2-7f77d44cb4f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the most popular Spanish recipe book available in paperback that are in stock.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: recipe\n[link] recipe book -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.285, 0.196, 0.31] in the image\nAnd my action is Action: SELECT\nValue: In Stock (7,640)" } ]

{ "bytes": "", "path": "./images/ddcbce13-4c42-4c40-99ab-2c58588f1ccf_f053b82b-ae9c-4cf9-9b60-45a18358f2bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Mens orange color Jacket and parkas with L Size and add to cart\nPrevious actions:\n[link] MEN -> HOVER\n[link] Jackets & Parkas -> CLICK\n[heading] Pocketable UV Protection 3D Cut Parka -> CLICK\n[checkbox] ORANGE -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.815, 0.186, 0.843, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b3a28e48-3912-4b0e-b3a9-d359da13864d_7f52cfc8-106d-40e8-ba47-2b67a7d462ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the NFL passing touchdown season stats.\nPrevious actions:\n[link] NFL . -> HOVER\n[link] Stats . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.414, 0.125, 0.428] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_ca113dc2-d281-4cf9-9793-9122d1170097.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[listitem] Little Caribbean, Brooklyn, NY, USA -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[combobox] Minimize my -> SELECT: Walking\n[button] Done button - Press enter key to submit travel pre... -> CLICK\n[label] Accessible Trip -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.441, 0.359, 0.477] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cfe20a-f008-48d3-b683-002ce7790616_b5eb98db-7b56-403f-8497-7bec0ac4fd57.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[combobox] Pick-up time -> SELECT: 9:00 am\n[combobox] Drop-off time -> SELECT: 6:00 pm\n[button] Search -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.25, 0.045, 0.258] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c997e24-d185-4730-84d6-f8cb512f4c03_7dd2e5c2-af14-4f5c-b147-58913a3bb612.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car options to pick up at any location near 10023 on april 12 at 3 am\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: 10023\n[span] , 10023 -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 12 -> CLICK\n[combobox] Pick Up Time -> SELECT: 3:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.337, 0.567, 0.38] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_747b1dea-1bd9-469d-8c76-54d19e3895ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[gridcell] June 18 -> CLICK\n[gridcell] June 21 -> CLICK\n[button] Search packages -> CLICK\n[button] Amenities -> CLICK\n[checkbox] Beachfront -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.121, 0.089, 0.128] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_06195ec9-afde-4c23-a8d3-db3666bc04a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] SAIL FROM -> CLICK\n[button] Seattle, WA -> CLICK\n[span] Dates -> CLICK\n[button] September 2023 -> CLICK\n[button] DURATION -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.378, 0.476, 0.616, 0.5] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f863168b-1d7e-4f51-9681-79891abc4b45_91007a2c-d94c-4c8d-ad80-1b8ca2c877db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a park in the National Park System that has a Junior Ranger Program for kids.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.354, 0.539, 0.366] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_73a60d20-1d3e-4b8a-bbea-d906c3a1faeb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[button]  -> CLICK\n[link] Western Digital WD_BLACK SN770 M.2 2280 1TB PCIe G... -> CLICK\n[button] ADD TO CART  -> CLICK\n[button] NO, THANKS -> CLICK\n[button] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.008, 0.39, 0.025] in the image\nAnd my action is Action: TYPE\nValue: 8GB Ram" } ]

{ "bytes": "", "path": "./images/36ab5d78-2f6b-47a6-ad88-3f6c8fdc3513_6d6e210e-ec5d-44db-bfde-0d32e4dd500a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the movies playing today at the theater closest to zip code 10001\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK\n[link] Find a Theatre -> CLICK\n[textbox] Find A Theatre -> TYPE: 10001\n[generic] Submit Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.444, 0.14, 0.458] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/867dc9d1-5017-4871-a52a-a1511f239628_8cae68b6-ff63-4283-8f18-a3a8e7ba48bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse movie trailers currently in theaters with \"fresh\" rating.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Trailers -> CLICK\n[link] VIEW ALL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.539, 0.182, 0.656, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bc45669b-6bed-4240-9d9b-6b5e45a7e6f3_6cf7c15e-7f95-413a-b4d7-01e26c009e43.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse xbox series x consoles that are used and between $200 and $400.\nPrevious actions:\n[combobox] Search for anything -> TYPE: xbox series x console\n[button] Search -> CLICK\n[input] -> CLICK\n[textbox] Minimum Value in $ -> TYPE: 200" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.58, 0.147, 0.608] in the image\nAnd my action is Action: TYPE\nValue: 400" } ]

{ "bytes": "", "path": "./images/08a0c5cc-41a9-4eb8-b3ea-91d9e26f8bd3_c0865eda-5f46-4b7d-bb9e-a5592539ec17.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get directions for the Koa resort campground in Arizona\nPrevious actions:\n[link] CAMPING AT KOA  -> CLICK\n[link] KOA RESORT CAMPGROUNDS  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.415, 0.149, 0.433] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_b46bd2d8-3838-4c77-9166-af6ada07da63.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK\n[span] All stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.225, 0.011, 0.776, 0.063] in the image\nAnd my action is Action: TYPE\nValue: organic strawberries" } ]

{ "bytes": "", "path": "./images/8e7b05d4-7dfb-4345-af2b-3e1dcd1c2ea2_413185f7-a793-4718-93ff-3c654b9f1c1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a map with charging stations in London.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Charging -> CLICK\n[link] Find Us -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.097, 0.216, 0.13] in the image\nAnd my action is Action: TYPE\nValue: London" } ]

{ "bytes": "", "path": "./images/a919aa15-2acf-4090-8468-1d3a0d6450b1_4f6b4130-a0b4-40e7-b91f-ffe8a6443083.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Need the cheapest small car on April 7, 10 am at Auckland airport for pick-up, return will be on April 10 at approx 5 pm.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 7 -> CLICK\n[combobox] Pick Up Time -> SELECT: 10:00 AM\n[textbox] mm/dd/yyyy -> CLICK\n[link] 10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.27, 0.891, 0.304] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

{ "bytes": "", "path": "./images/d6a0ab7c-f0d7-4ff7-9d42-55b44b5e7f74_32e030ec-b522-40ed-9217-95c09cb73aee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the artist profile of M S Subbulakshmi and play all from the top tracks.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: m s subbulakshmi\n[button] Search -> CLICK\n[link] M.S. Subbulakshmi -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.128, 0.409, 0.192, 0.419] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92cd371-0bd2-4ac3-82e4-7fdaac46b626_9bf58be2-cf7a-4732-af73-5e7c17b70540.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\n[combobox] Search products and services -> TYPE: zyrtec\n[button] Search for zyrtec -> CLICK\n[img] Zyrtec 24 Hour Allergy Relief Tablets with 10 mg C... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.26, 0.381, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4aaf59c0-889a-406c-b0c2-454d7670e04f_fbede47e-7ae1-4ed2-9cc9-0d0d7a55577a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the TSA Guidelines to travel with Children\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Traveling with children -> CLICK\n[link] sit on a parent’s lap -> CLICK\n[link] approved car seat -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.343, 0.918, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_a03b4d90-3f1b-4a34-a8ac-dda1d6e458e1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: book a reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[span] Chicago, IL - Lincoln Park -> CLICK\n[i] -> CLICK\n[i] -> CLICK\n[button] Go to next month -> CLICK\n[button] 2023-04-05 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.704, 0.333, 0.908, 0.358] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

{ "bytes": "", "path": "./images/8b743c63-2a99-4c29-93ef-af920dab9535_73592b67-ffcd-4021-8342-1ec06c4a56ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse monthly parking rates near the Museum of Modern Art.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: MOMA\n[option] Museum of Modern Art (MoMA)   11 West 53rd St, New... -> CLICK\n[link] MONTHLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.53, 0.328, 0.557] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1fa9bb3-6e2c-485b-90f1-2a54510bf358_9124ca10-aa2c-45cb-870b-29a580fbb2f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking near Disneyland that has EV charging.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Disneyland" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.362, 0.754, 0.389] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b54b029-bff8-49a7-acca-c57163f14279_4cadd81b-2ad9-43cc-a6ae-7785bf77b8b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find music events in Los Angeles today\nPrevious actions:\n[textbox] Search events -> TYPE: music\n[combobox] autocomplete -> TYPE: los angeles \n[div] Los Angeles -> CLICK\n[path] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.131, 0.237, 0.158] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_06e9c069-d60e-483d-936f-6a14544521fd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.427, 0.154, 0.443] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_3dcc458a-5ca1-4057-a628-51580cd69e87.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[span] London Paddington -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 8 -> CLICK\n[listbox] hour -> SELECT: 14\n[listbox] minutes -> SELECT: 00" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.193, 0.327, 0.22] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_c8b5a410-7058-493a-bb19-342825c78916.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: LONDON\n[button] London, GB (LON - All Airports) -> CLICK\n[textbox] Depart -> CLICK\n[button] Saturday, July 1, 2023 -> CLICK\n[button] Wednesday, July 5, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.227, 0.481, 0.251] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c0eeead1-f8ea-4819-a6da-ef0108b40c89_df415b14-e121-43a8-8548-058989210645.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sign Allan Smith for email offers with the email [email protected] and zip code 10001\nPrevious actions:\n[a] -> CLICK\n[textbox] First Name (required) -> TYPE: Allan\n[textbox] Last Name (required) -> TYPE: Smith\n[textbox] Email Address (required) -> TYPE: [email protected]\n[textbox] Confirm Email Address (required) -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.319, 0.754, 0.343] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_749c3a9d-c4aa-4517-8e1f-ec5fa5845eb1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[combobox] Time -> SELECT: 8:00 PM\n[combobox] Size -> SELECT: 4 guests\n[button] Update search -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] American -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.424, 0.812, 0.469] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50f1e384-4b63-4827-a670-cd19f5a2c710_72893745-5e04-4e66-8557-81416454ade4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find schedule for Long Island Rail Road & Metro-North Railroad from Bay Shore to Breakneck Ridge on Thu, Mar 23, 08:37 AM.\nPrevious actions:\n[link] Schedules -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.259, 0.474, 0.291] in the image\nAnd my action is Action: TYPE\nValue: Bay Shore" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_0c87b2bb-027a-4daa-867f-bc0d3d2382fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[span] -> CLICK\n[button] City -> CLICK\n[span] -> CLICK\n[button] Hiring Type -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.845, 0.324, 0.966, 0.36] in the image\nAnd my action is Action: SELECT\nValue: Most recent" } ]

{ "bytes": "", "path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_7d52e0c3-c338-4214-889f-318d4ce15d5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[generic] Vehicle Type * -> CLICK\n[p] SUVs & Wagons -> CLICK\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $21.99/Day -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.56, 0.777, 0.594] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_ba7b7ba5-9604-43af-8fbe-fea243c8bb58.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.04, 0.106, 0.047] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/981fdb06-2352-439f-a6d0-ccaa857c7a54_609108a1-eaaf-4f18-8442-8fec437811f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the trade-in options for PS4.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Consoles -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: PlayStation 4 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.027, 0.378, 0.045] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_7d2559d3-fa15-4fb3-ac78-fdbd51dcc976.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.195, 0.18, 0.829, 0.189] in the image\nAnd my action is Action: TYPE\nValue: seattle" } ]

{ "bytes": "", "path": "./images/d1942a73-745f-44c5-ba30-0d0c7925f5d2_8203c2a7-4502-4ff2-ac52-1440d2c847ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a comedy movie streaming on Netflix and add to watchlist.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Netflix streaming -> CLICK\n[svg] -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.285, 0.43, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8089c50-e80c-4532-82a1-96009f485c57_3484246f-8de9-4c54-884b-0ffcaf153cb2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Women's t-shirt for $40-$60 and add it to Wishlist, stop at the Login screen.\nPrevious actions:\n[link] WOMEN -> CLICK\n[tab] Tops -> CLICK\n[link] T-Shirts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.475, 0.488, 0.494, 0.509] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e1a344d-a27b-4613-8863-7afad0829b23_1295eaa5-670e-4aa2-b430-998bd21fda2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest washable blue rug under 2'x3' size.\nPrevious actions:\n[span] Color -> CLICK\n[link] Blue (237) -> CLICK\n[span] Size -> CLICK\n[link] Under 2'x3' (38) -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.303, 0.974, 0.331] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74e653f0-aeea-4f01-8d80-c5846fae0c1c_ad513ef7-dd90-4c7b-b00b-ec97683ed0fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the Recommended Gaming PCs for someone who plays Fortnite, Overwatch and GTA V at 4k\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK\n[div] Remove -> CLICK\n[div] Remove -> CLICK\n[p] Remove -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.642, 0.494, 0.72, 0.522] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cc81f50-465c-4d77-8fd7-d81fe1ffde84_ab469efb-c6dc-47f7-9426-0938350e8063.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\n[link] Live TV -> CLICK\n[button] Broadcast TV Spokane (3) -> CLICK\n[textbox] Search -> TYPE: 99201\n[button] Antenna -> CLICK\n[button] Broadcast TV Spokane (3) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.241, 0.779, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13d78369-994a-4202-a9ed-8361e1fdea9d_90936bb2-dd00-403c-b782-4b006604b686.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse bluetooth headphones with active noise-cancellation.\nPrevious actions:\n[searchbox] Search Site -> TYPE: headphones\n[button]  -> CLICK\n[span] Active -> CLICK\n[button] APPLY -> CLICK\n[span] Bluetooth -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.619, 0.192, 0.636] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e3c7ad0-f138-490e-918e-42bcce9f55a9_af945b27-92ce-453c-9c39-59ce63a8190a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a harry potter book to my wishlist.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: Harry Potter" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.754, 0.056, 0.863, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_671088e4-09b7-41ef-b93b-264eead46e7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[generic] Refine by Category: Xbox Series X|S -> CLICK\n[link] Shop Pre-Orders -> CLICK\n[button] Franchise -> CLICK\n[checkbox] Resident Evil Resident Evil -> CLICK\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.33, 0.177, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_51f6ca95-3089-4b4d-b3e4-ccb627fba834.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\n[span] Matthews Winery -> CLICK\n[link] Book now Indoor Reservation, Two-hour indoor seati... -> CLICK\n[button] 2023-03-31 -> CLICK\n[i] -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.462, 0.202, 0.5, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aedabbf-a7b4-4da7-8eaf-9e159a3ec99b_fe43de0e-b79f-4f44-b856-0087c33dbbf4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: review the dinner menu of La Bergamote restaurant in Hell's Kitchen.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.056, 0.615, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a40f4c8-7aa6-4be4-abbe-24a0b511dc0e_d9556517-1528-497f-b701-9edc906c9343.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for hiking boots and filter the results to show only those with a waterproof rating of at least 3 stars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.085, 0.128, 0.119] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_e62f4bfc-502c-4f11-a37e-f64cc8febe6e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.038, 0.111, 0.055] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ed8cd2a-b0f8-4ccf-9d48-1ddfba4f5e58_5bf6ca81-46f9-4681-b086-fc23bd8fb027.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find motorcycle parking near Radio City Music Hall.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.252, 0.592, 0.277] in the image\nAnd my action is Action: TYPE\nValue: radio city music hall" } ]

{ "bytes": "", "path": "./images/d29fd2a4-2305-4276-8a0e-2599291d0a17_9d01e4d4-cf3a-47ce-98a3-26f66887e574.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the list of reviews I wrote about my games.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.482, 0.0, 0.589, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_bf663b13-de7d-4099-9aa6-cdd33f15c1f3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[em] Plymouth -> CLICK\n[button] Depart at 8:20 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 28, 2023 -> CLICK\n[combobox] Hour -> TYPE: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.199, 0.471, 0.246, 0.506] in the image\nAnd my action is Action: TYPE\nValue: 30" } ]

{ "bytes": "", "path": "./images/90a0f029-c1af-4dd7-8ccd-c4c2a74e8731_32d68cd0-e6e1-470e-aa15-4f34d99a7f9a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: san francisco\n[span] San Francisco, CA -> CLICK\n[textbox] Departure -> CLICK\n[button] Tuesday, April 11, 2023 -> CLICK\n[button] Friday, April 14, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.628, 0.622, 0.653] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccd8d9f9-65f1-42ac-a699-5db7e380c760_36d6ee3c-4be7-4367-a004-181ac15edf7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Washington airports to New York airports and only show those with scheduled status.\nPrevious actions:\n[link] Flight Tracking -> HOVER\n[link] Flight Finder -> CLICK\n[textbox] Origin -> TYPE: Washington\n[div] Washington -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.208, 0.909, 0.235] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_2c6307f7-6697-4a4f-8e2e-73682ce6f1a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[button] Select Truck -> CLICK\n[input] -> TYPE: 250\n[button] Continue to Location -> CLICK\n[select] Select a Pick-up Time -> SELECT: 04:00 PM\n[select] 04:30 PM -> SELECT: 04:30 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.25, 0.915, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fb1c90e-a494-4de9-86ac-d4e5366869c4_65a752cb-43ca-4607-bc88-ec49b8285742.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a virtual consultation for Solar Roof. The name is James Smith. The address is 123 st rd. The emial address is [email protected]\nPrevious actions:\n[link] Solar Roof -> CLICK\n[link] Schedule a virtual consultation -> CLICK\n[textbox] First Name -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.459, 0.355, 0.471] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/a2b159c8-86d0-4b76-9244-f19cc41d5ad8_519c155a-6823-4c59-8683-a50bb52b637a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a Medical book related to Diseases & Disorders to basket.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.059, 0.129, 0.079] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aab91310-0100-4a40-98e9-720c53199bff_b3929fbc-0cb0-4e73-8144-eab7ac9ebb5e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find mens hiking shoes under $100 in size 10 that has biggest discount.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: mens hiking shoes\n[input] -> CLICK\n[div] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.427, 0.102, 0.439] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_5f14babf-98ed-4a84-a458-84233cd7bb3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.592, 0.222, 0.781, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_2be3b5da-bcc5-4de4-b691-c7115cd419f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] Email address -> TYPE: [email protected]\n[textbox] Confirm email address -> TYPE: [email protected]\n[input] -> TYPE: 1111111111111111\n[textbox] Address 1 -> TYPE: the home of joe bloggs\n[textbox] City -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.401, 0.95, 0.464] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/5c91b907-39db-49c3-af73-5eb5c2390a93_443327ef-bef2-4f4c-8aa3-77669cbad78a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Modesto California and set is as my store.\nPrevious actions:\n[link] Find a store -> CLICK\n[searchbox] Search carmax locations. -> TYPE: california\n[button] Search. -> CLICK\n[div] Modesto -> CLICK\n[link] Visit Modesto store details. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.164, 0.46, 0.187] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ac59be41-36c3-44c5-8e1f-ffb9461ba980_fad40521-7262-4bf8-9611-be44c197681a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for all Alternative Concerts taking place in New York City.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.246, 0.266, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/013faefc-26df-4eeb-be59-5638c5f9dc72_c696d8ea-3bb7-4e69-9be9-d9f7228436db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a room at the Marriott Bonvoy resort in the Caribbean for a 10-day stay starting on May 5th.\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Carribbean" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.358, 0.067, 0.661, 0.114] in the image\nAnd my action is Action: CLICK" } ]